Method and device for recognizing abnormal working resistance of hydraulic support and electronic equipment

Abstract

The invention provides a hydraulic support working resistance abnormity identification method and device and electronic equipment, and the method comprises the steps: employing a target prediction model to predict the opening probability of a safety valve of each hydraulic support in a future target duration based on the working data of a plurality of hydraulic supports in a current time period in the recovery work; wherein the current time period comprises the current moment; determining a first risk sub-index value according to each opening probability; performing first analysis on the mining data of the stoping work in the current time period to obtain a second risk sub-index value; performing second analysis on the target working resistance cloud charts of the plurality of hydraulic supports at the current moment to obtain a third risk sub-index value; and based on the first risk sub-index value, the second risk sub-index value and the third risk sub-index value, identifying target anomaly types of the plurality of hydraulic supports. Therefore, the working resistance stress abnormity result of the hydraulic support can be automatically and quickly identified, and the timeliness and effectiveness of working resistance abnormity identification of the hydraulic support are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and particularly relates to a method for identifying abnormal working resistance of hydraulic supports. Background Art

[0002] In the underground operation scenario of a mine, the geological conditions are complex and changeable. During the ore mining process, the safety of the roadway structure undoubtedly occupies a crucial position. As a key device for supporting the roadway and protecting the safety of workers, the hydraulic support plays an irreplaceable role. During the ore mining operation, various pressures borne by the roadway are likely to cause abnormal stress conditions in the working resistance of the hydraulic support. If these abnormal conditions are not detected and properly handled in a timely manner, it is very likely to cause the failure of the support structure and even lead to mine accident. Therefore, it is of great significance to monitor and warn against the abnormal working resistance of the hydraulic support. Summary of the Invention

[0003] The present application aims to at least solve one of the technical problems in the related art to some extent.

[0004] To this end, the first object of the present application is to propose a method for identifying abnormal working resistance of hydraulic supports.

[0005] The second object of the present application is to propose a device for identifying abnormal working resistance of hydraulic supports.

[0006] The third object of the present application is to propose an electronic device.

[0007] The fourth object of the present application is to propose a computer-readable storage medium.

[0008] The fifth object of the present application is to propose a computer program product.

[0009] To achieve the above object, the first aspect embodiment of the present application proposes a method for identifying abnormal working resistance of hydraulic supports, including: Based on the working data of multiple hydraulic supports in the current time period during the coal mining work, using a target prediction model, predicting the opening probability of the safety valves of each of the hydraulic supports within a future target time period; wherein, the current time period includes the current moment; According to each of the opening probabilities, determining a first risk sub-index value; wherein, the first risk sub-index value is determined based on the number of target hydraulic supports among the multiple hydraulic supports whose opening probabilities meet the set conditions and whose installation positions are continuously adjacent; Performing a first analysis on the mining data of the coal mining work in the current time period to obtain a second risk sub-index value; Performing a second analysis on the target working resistance cloud map of the multiple hydraulic supports at the current moment to obtain a third risk sub-index value; Based on the first risk sub-indicator value, the second risk sub-indicator value and the third risk sub-indicator value, target abnormality types of the plurality of hydraulic supports are identified.

[0010] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a device for identifying abnormal working resistance of a hydraulic support, the device comprising: A prediction module is used to predict the opening probability of the safety valve of each hydraulic support within a future target time period based on the working data of multiple hydraulic supports in the current time period during the mining work, using a target prediction model; wherein the current time period includes the current moment; A first determination module is used to determine a first risk sub-index value according to each of the opening probabilities; wherein the first risk sub-index value is determined based on the number of target hydraulic supports whose opening probabilities meet set conditions and whose layout positions are continuously adjacent to each other among the multiple hydraulic supports; A first analysis module is used to perform a first analysis on the mining data of the mining work in the current time period to obtain a second risk sub-indicator value; A second analysis module is used to perform a second analysis on the target working resistance cloud diagrams of the plurality of hydraulic supports at the current moment to obtain a third risk sub-indicator value; An identification module is used to identify target abnormality types of the multiple hydraulic supports based on the first risk sub-indicator value, the second risk sub-indicator value and the third risk sub-indicator value.

[0011] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect embodiment above.

[0012] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect embodiment above.

[0013] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect of the present application.

[0014] The method for identifying abnormal working resistance of hydraulic supports provided in this application predicts the opening probability of the safety valves of each hydraulic support within the future target time period by using a target prediction model based on the working data of multiple hydraulic supports during the current time period in the coal mining operation; wherein, the current time period includes the current moment; according to each opening probability, a first risk sub-index value is determined; wherein, the first risk sub-index value is determined based on the number of target hydraulic supports among multiple hydraulic supports whose opening probabilities meet the set conditions and whose layout positions are continuously adjacent; a first analysis is performed on the mining data of the coal mining operation during the current time period to obtain a second risk sub-index value; a second analysis is performed on the target working resistance cloud map of multiple hydraulic supports at the current moment to obtain a third risk sub-index value; based on the first risk sub-index value, the second risk sub-index value, and the third risk sub-index value, the target abnormal type of multiple hydraulic supports is identified. Thus, by combining the working data of hydraulic supports, the mining data of the coal mining operation, and the working resistance cloud map of hydraulic supports, the abnormal result of the working resistance stress of hydraulic supports can be automatically and quickly identified, improving the timeliness and effectiveness of identifying abnormal working resistance of hydraulic supports.

[0015] Additional aspects and advantages of this application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of this application will become apparent and be readily understood from the following description of embodiments in conjunction with the drawings, wherein: Figure 1 is a schematic flow chart of the method for identifying abnormal working resistance of hydraulic supports provided in an embodiment of this application; Figure 2 is a schematic flow chart of the method for identifying abnormal working resistance of hydraulic supports provided in another embodiment of this application; Figure 3 is a schematic flow chart of the method for identifying abnormal working resistance of hydraulic supports provided in another embodiment of this application; Figure 4 is a schematic diagram of the target mining area provided in this application; Figure 5 is a schematic diagram of the first working resistance cloud map provided in this application; Figure 6 is a schematic structural diagram of the device for identifying abnormal working resistance of hydraulic supports provided in another embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0018] With the rapid development of intelligent perception technologies and equipment for hydraulic supports, the electro-hydraulic control system can achieve real-time monitoring and collection of the inclination angle, load, and attitude of hydraulic supports throughout the coal mining face to obtain a large amount of perception data. Based on this, relevant technicians have applied various types of wired and wireless perception elements for the support state of hydraulic supports and developed a working resistance stress monitoring device based on resistance change / time change to monitor the stress condition of hydraulic supports. However, the above-mentioned working resistance stress monitoring device lacks the ability to respond immediately in a dynamically changing environment and cannot meet the requirements of modern engineering for high-precision and real-time monitoring. Moreover, when processing relevant data of hydraulic supports, due to the large amount of data, the storage performance and query performance of the database are severely degraded during actual use, resulting in various problems such as page freezing, slow data query, and data loss, and it is impossible to comprehensively perceive, quickly evaluate, and give early warnings about the working state or working data of the supports in a timely manner.

[0019] To address at least one of the above problems, the present application proposes a method, device, and electronic device for identifying abnormal working resistance of hydraulic supports.

[0020] The method, device, and electronic device for identifying abnormal working resistance of hydraulic supports according to embodiments of the present application will be described below with reference to the accompanying drawings.

[0021] Figure 1 It is a schematic flowchart of the method for identifying abnormal working resistance of hydraulic supports provided by an embodiment of the present application.

[0022] In the embodiments of the present application, the method for identifying abnormal working resistance of hydraulic supports is configured in a device for identifying abnormal working resistance of hydraulic supports for illustration. The device for identifying abnormal working resistance of hydraulic supports can be applied to any electronic device so that the electronic device can execute the function of identifying abnormal working resistance of hydraulic supports.

[0023] Among them, the electronic device can be any device with computing capabilities, such as a personal computer (abbreviated as PC), an industrial computer, a host computer, a mobile terminal, a server, etc. The mobile terminal can be, for example, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc., which are hardware devices with various operating systems, touch screens, and / or display screens.

[0024] As Figure 1 shown, the method includes the following steps: Step S101: Based on the working data of multiple hydraulic supports during the current period in the coal mining operation, use the target prediction model to predict the opening probabilities of the safety valves of each hydraulic support within the future target duration.

[0025] Among them, the current period may include the current moment. Optionally, in some embodiments, the current period may include multiple target moments. At this time, it should be noted that the multiple target moments include the current moment.

[0026] Among them, in the coal mining operation, the hydraulic support can be used to support the coal mining face, and the hydraulic support may include a front column and a rear column. It should be noted that the number of hydraulic supports in this application is not limited.

[0027] Optionally, in some embodiments, when the current period includes multiple target moments, the working data may include, but is not limited to: the support numbers of each hydraulic support, the left column resistance value (i.e., the working resistance of the left column) and the right column resistance value (i.e., the working resistance of the right column) of any hydraulic support at each target moment, the left initial support force and the right initial support force of any hydraulic support at each target moment, the target working stage of any hydraulic support at each target moment and the start time of the target working stage (denoted as the first start time in this application), the start time (denoted as the second start time in this application) and the end time when the safety valve is in the open state during the most recent safety valve opening cycle in the historical record corresponding to any hydraulic support at each target moment, the live column height data when the safety valve is in the open state during the most recent safety valve opening cycle in the historical record corresponding to any hydraulic support at each target moment, and so on.

[0028] Among them, the support number is used to uniquely identify the corresponding hydraulic support.

[0029] Among them, the target working stage may be one of the ascending column stage, the descending column stage, the supporting stage, and the moving support stage.

[0030] Among them, the safety valve opening cycle can indicate the frequency at which the safety valve of the corresponding hydraulic support automatically opens and unloads during system pressure fluctuations.

[0031] Optionally, in some embodiments, the target prediction model may include a first bidirectional LSTM (Long Short-Term Memory) layer, a Dropout layer, a second bidirectional LSTM layer, and a Sigmoid layer.

[0032] Among them, the target duration can be preset, such as 10s, 15s, etc., and this application does not limit this. It should be noted that the future target duration can be the target duration after the current time. For example, if the current time is t, the future target duration refers to 10s after t.

[0033] The opening probability can be used to indicate the possibility of the safety valve of the corresponding hydraulic support being opened.

[0034] In the embodiment of the present application, based on the working data of multiple hydraulic supports in the current time period during mining work, a target prediction model can be used to predict the opening probability of the safety valve of each hydraulic support within the future target time period.

[0035] Optionally, in some embodiments, data preprocessing may be performed on the working data of multiple hydraulic supports in the current time period, wherein the data preprocessing may include normalization, missing value processing, outlier processing, etc., which is not limited in the present application.

[0036] Step S102: determining a first risk sub-indicator value according to each activation probability.

[0037] The first risk sub-index value may be determined based on the number of target hydraulic supports whose opening probabilities meet set conditions and whose layout positions are continuously adjacent to each other among the multiple hydraulic supports.

[0038] Among them, the setting conditions can be pre-set, and this application does not limit the setting of the setting conditions.

[0039] Optionally, in some embodiments, the setting condition may be, for example, that the start probability is greater than a set probability threshold, wherein the set probability threshold may be pre-set, such as 0.8, 0.75, etc., and this application does not limit this.

[0040] Optionally, in some embodiments, for any hydraulic support among multiple hydraulic supports, when the probability of opening of the safety valve of the hydraulic support within the future target time period meets the set conditions, the hydraulic support is determined to be the second hydraulic support; when the hydraulic support is determined to be the second hydraulic support, determine whether there is a hydraulic support whose opening probability meets the set conditions from the hydraulic supports adjacent to the layout position of the second hydraulic support, and if so, determine the second hydraulic support to be the target hydraulic support; and then determine the first risk sub-indicator value based on the number of target hydraulic supports with consecutive adjacent layout positions among the multiple hydraulic supports.

[0041] It should be noted that, when the hydraulic support is determined to be the second hydraulic support, if there is no hydraulic support whose opening probability meets the set conditions among the hydraulic supports adjacent to the second hydraulic support, it is determined that the second hydraulic support is not the target hydraulic support.

[0042] As an example, assume that the number of hydraulic supports is n. For the j-th hydraulic support among the n hydraulic supports, when the opening probability of the safety valve of the j-th hydraulic support within the future target time period meets the set conditions, determine the j-th hydraulic support as the second hydraulic support; in the case of determining the j-th hydraulic support as the second hydraulic support, determine whether there is a hydraulic support with an opening probability meeting the set conditions among the hydraulic supports adjacent to the installation position of the j-th hydraulic support. If there is, then the j-th hydraulic support is the target hydraulic support; otherwise, determine that the j-th hydraulic support is not the target hydraulic support; finally, determine the corresponding risk score according to the maximum number of target hydraulic supports with continuously adjacent installation positions among multiple hydraulic supports, and determine this risk score as the first risk sub-index value. For example, assume that n is 150, and the 7th to 17th hydraulic supports are target hydraulic supports with continuously adjacent installation positions and an opening probability meeting the set conditions, the 80th to 89th hydraulic supports are target hydraulic supports with continuously adjacent installation positions and an opening probability meeting the set conditions, and the 135th to 147th hydraulic supports are target hydraulic supports with continuously adjacent installation positions and an opening probability meeting the set conditions. Then the maximum number of target hydraulic supports with continuously adjacent installation positions and an opening probability meeting the set conditions among the above 150 hydraulic supports is 13 (= 147 - 135 + 1). Then, the corresponding risk score can be determined according to this maximum number, and this risk score is determined as the first risk sub-index value.

[0043] Among them, it should be noted that a corresponding relationship between the maximum number of target hydraulic supports with continuously adjacent installation positions among multiple hydraulic supports and the risk score can be established in advance and this corresponding relationship can be saved. Furthermore, after determining the maximum number, the above corresponding relationship can be queried to obtain the corresponding risk score.

[0044] As an example, the maximum number of target hydraulic supports with continuously adjacent installation positions among multiple hydraulic supports and their corresponding risk scores are shown in Table 1: Table 1 Maximum number and its corresponding risk score

[0045] It should be noted that the above example of the maximum number and its corresponding risk score is only exemplary. In actual applications, it can also be other situations, and the present application does not limit this.

[0046] Step S103, perform a first analysis on the mining data of the coal mining work in the current time period to obtain the second risk sub-index value.

[0047] Among them, the mining data can include but is not limited to the shearer number of the shearer, the mining progress, the mining height, the traction direction of the current operating shearer, and the support stiffness of each hydraulic support.

[0048] Among them, the shearer number is used to uniquely identify the corresponding shearer.

[0049] The mining progress represents the daily mining advance distance and is used to indicate the coal mining speed. The traction direction is used to indicate the working direction of the corresponding shearer.

[0050] The support stiffness can be used to measure the support ability of the corresponding hydraulic support to the roof.

[0051] As a possible implementation, based on the mining data, the Mining FEM model (Finite Element Method Model in Mining) can be used to obtain the second risk sub-index value.

[0052] It should be noted that the core functions of the Mining FEM model include the roof pressure distribution simulation function, the roadway deformation analysis function, and the geological risk coefficient calculation function. Among them, the roof pressure distribution simulation function can dynamically calculate the roof pressure distribution according to the mining height and mining progress, and predict the index value of the potential roof subsidence risk; the roadway deformation analysis function can evaluate the stability and deformation trend of the roadway surrounding rock in combination with the support stiffness of the hydraulic support, and obtain the roadway deformation risk index value; the geological risk coefficient calculation function can output the geological risk coefficient based on the index value of the roof subsidence risk and the index value of the roadway deformation risk, which is denoted as the second risk sub-index value in this application.

[0053] Step S104: Perform a second analysis on the target working resistance cloud map of multiple hydraulic supports at the current moment to obtain the third risk sub-index value.

[0054] Among them, the target working resistance cloud map can be used to indicate the distribution of resistance values of multiple hydraulic supports at different positions.

[0055] In the embodiment of this application, a second analysis can be performed on the target working resistance cloud map of multiple hydraulic supports to obtain the third risk sub-index value.

[0056] Step S105: Based on the first risk sub-index value, the second risk sub-index value, and the third risk sub-index value, identify the target abnormal types of multiple hydraulic supports.

[0057] Among them, the target abnormal types can be, but are not limited to, low risk, medium risk, high risk, etc.

[0058] As an example, the first risk sub - index value, the second risk sub - index value, and the third risk sub - index value can be weighted and summed to obtain a target coefficient. Then, based on the target coefficient, the corresponding abnormal type can be determined, and this abnormal type can be determined as the target abnormal type of multiple hydraulic supports.

[0059] As an example, the target distance interval to which the target coefficient belongs can be determined from multiple set value ranges, and the abnormal type corresponding to the target distance interval can be determined as the target abnormal type of multiple hydraulic supports.

[0060] Among them, the set value ranges can be preset, and the present application does not limit the value range of the set value ranges.

[0061] It should be noted that any set value range can have a corresponding abnormal type. In one example, the set value ranges and the corresponding abnormal types are shown in Table 1: Table 2 Set value ranges and corresponding abnormal types

[0062] As shown in Table 1, when the target distance interval to which the target coefficient belongs is (0.5, 0.75], then the abnormal type corresponding to this target distance interval is determined as the target abnormal type of the hydraulic support.

[0063] It should be noted that the above examples of the set value ranges and the corresponding abnormal types are only exemplary, and the present application does not limit the set value ranges and the corresponding abnormal types.

[0064] As a possible implementation manner, after obtaining the first risk sub - index value, the second risk sub - index value, and the third risk sub - index value, the target weights of the first risk sub - index value, the second risk sub - index value, and the third risk sub - index value can be determined respectively based on the first risk sub - index value, the second risk sub - index value, and the third risk sub - index value.

[0065] As an example, assuming that the first risk sub - index value is R1, the second risk sub - index value is R2, and the third risk sub - index value is R3, the initial weights of the above - mentioned respective index values can be determined according to the following formulas: ; (1) ; (2) ; (3) Among them, represents the initial weight of the first risk sub - index value, represents the initial weight of the second risk sub - index value, represents the initial weight of the third risk sub - index value; Furthermore, the above initial weights are normalized to obtain the target weights of the above index values.

[0066] In this way, the real-time calibration of the weights of various indicators can be achieved. By dynamically adjusting the weights of various indicator values, the rationality of weight distribution can be improved, as well as the accuracy and effectiveness of subsequent corresponding decisions.

[0067] Optionally, in some embodiments, the corresponding target response measures can be determined and deployed according to the target abnormality type. As an example, assuming that the target abnormality type is low risk, the hydraulic support can continue to be routinely monitored; when the target abnormality type is medium risk, the sound and light alarm system can be controlled to sound and light alarm to prompt relevant staff to reduce the mining speed to the target speed (such as 50% of the mining speed, etc.); when the target abnormality type is high risk, the operating equipment in the mining work (such as mining machines, transportation equipment, etc.) can be controlled to stop running, so that relevant staff can carry out support reinforcement (such as grouting / repairing, etc.).

[0068] The method for identifying abnormal working resistance of hydraulic supports in the embodiment of the present application is to predict the opening probability of the safety valve of each hydraulic support within the future target time length by using the target prediction model based on the working data of multiple hydraulic supports in the current time period during the mining work; wherein the current time period includes the current moment; according to each opening probability, determine the first risk sub-index value; wherein the first risk sub-index value is determined based on the number of target hydraulic supports whose opening probability meets the set conditions and whose layout positions are continuously adjacent among the multiple hydraulic supports; perform a first analysis on the mining data of the mining work in the current time period to obtain a second risk sub-index value; perform a second analysis on the target working resistance cloud map of multiple hydraulic supports at the current moment to obtain a third risk sub-index value; based on the first risk sub-index value, the second risk sub-index value and the third risk sub-index value, identify the target abnormal type of multiple hydraulic supports. Thus, the working data of the hydraulic supports, the mining data of the mining work and the working resistance cloud map of the hydraulic supports can be combined to automatically and quickly identify the abnormal working resistance stress results of the hydraulic supports, thereby improving the timeliness and effectiveness of the recognition of abnormal working resistance of the hydraulic supports.

[0069] In order to clearly illustrate how, in the above embodiment of the present application, based on the working data of multiple hydraulic supports in the current time period during mining work, a target prediction model is used to predict the opening probability of the safety valve of each hydraulic support within the future target time period, the present application also proposes a method for identifying abnormal working resistance of a hydraulic support.

[0070] Figure 2 A flow chart of a method for identifying abnormal working resistance of a hydraulic support provided in another embodiment of the present application.

[0071] As Figure 2 shown, the method includes the following steps: Step S201, statistically analyze the working data of multiple hydraulic supports in the current time period to obtain at least one statistical feature.

[0072] It should be noted that the explanations of the hydraulic support, the current time period, and the working data in step S101 also apply to this embodiment and will not be elaborated here.

[0073] Optionally, in some embodiments, when the current time period includes multiple target time periods, the working data includes at least one of the following: The left column resistance value and the right column resistance value of each hydraulic support at any target moment; The left initial support force and the right initial support force of each hydraulic support at any target moment; The target working stage of each hydraulic support at any target moment and the first start time of the target working stage; The second start time and the end time when the safety valve is in the open state during the most recent safety valve opening cycle in the historical record corresponding to each hydraulic support at any target moment; The live column height data when the safety valve is in the open state during the most recent safety valve opening cycle in the historical record corresponding to each hydraulic support at any target moment; Correspondingly, the statistical feature may include at least one of the following: The target resistance value of each hydraulic support at any target moment; wherein, the target resistance value is determined based on the left column resistance value and the right column resistance value of the corresponding hydraulic support; The initial support force qualification rate of multiple hydraulic supports at any target moment; wherein, the initial support force qualification rate is determined based on the left initial support force and the right initial support force of multiple hydraulic supports; The working cycle time vector of each hydraulic support at any target moment; wherein, the working cycle time vector is generated based on the target working stage of the corresponding hydraulic support at the corresponding target moment and the first start time of the target working stage; The target duration of each hydraulic support at any target moment; wherein, the target duration is based on the second start time and the end time when the safety valve is in the open state during the most recent safety valve opening cycle in the corresponding historical record of the corresponding hydraulic support; The target live column shrinkage amount of each hydraulic support at any target moment; wherein, the target live column shrinkage amount is determined based on the live column height data when the safety valve is in the open state during the most recent safety valve opening cycle in the corresponding historical record of the corresponding hydraulic support.

[0074] Optionally, in some embodiments, the target resistance value may be the average of the left column resistance value and the right column resistance value of the corresponding hydraulic support.

[0075] Optionally, in some embodiments, for any target time, the determination process of the initial support force qualification rate of multiple hydraulic supports at the target time may be as follows: for any hydraulic support, determine whether the left initial support force and the right initial support force of the hydraulic support at the target time are both qualified; when the left initial support force and the right initial support force of the hydraulic support at the target time are both qualified, determine the hydraulic support as the first hydraulic support with qualified initial support force; count the first hydraulic supports among the multiple hydraulic supports to obtain the first quantity; according to the first quantity and the quantity of the multiple hydraulic supports, determine the initial support force qualification rate of the multiple hydraulic supports at the target time.

[0076] As an example, assume that the number of hydraulic supports is n. For the i-th hydraulic support, when the left initial support force F 左 satisfies the following conditions: F 左min ≤F 左 ≤F 左max ; (4) where F 左min and F 左max are respectively the minimum and maximum values that the left initial support force of the i-th hydraulic support can take; then the left initial support force of the i-th hydraulic support at the target time is qualified; When the left initial support force F 右 of the i-th hydraulic support at the target time satisfies the following conditions: F 右min ≤F 右 ≤F 右max ; (5) where F 右min and F 右max are respectively the minimum and maximum values that the right initial support force of the i-th hydraulic support can take; then the right initial support force of the i-th hydraulic support at the target time is qualified; When it is determined that both the left initial support force and the right initial support force of the i-th hydraulic support at the target time are qualified, determine the i-th hydraulic support as the first hydraulic support with qualified initial support force; finally, count the first hydraulic supports among the multiple hydraulic supports to obtain the first quantity; determine the ratio of the first quantity to the quantity of the multiple hydraulic supports as the initial support force qualification rate of the multiple hydraulic supports at the target time.

[0077] It should be noted that the minimum values that the left initial support force of the same hydraulic support can take and the minimum values that the right initial support force of the same hydraulic support can take may be the same or different. Similarly, the maximum values that the left initial support force of the same hydraulic support can take and the maximum values that the right initial support force of the same hydraulic support can take may be the same or different. The minimum values that the left initial support force of different hydraulic supports can take may be the same or different. Similarly, the maximum values that the left initial support force of different hydraulic supports can take may be the same or different; the minimum values that the right initial support force of different hydraulic supports can take may be the same or different; the maximum values that the right initial support force of different hydraulic supports can take may be the same or different.

[0078] Optionally, in some embodiments, for any hydraulic support, the generation process of the working cycle time vector of the hydraulic support at any target moment may include: for any target moment, based on the time difference between the current time and the first start time of the target working stage where the hydraulic support is located at the target moment, determining the first duration of the target working stage where the hydraulic support is located at the target moment; generating the working cycle time vector of the hydraulic support at the target moment according to the first duration of the target working stage where the hydraulic support is located at the target moment.

[0079] As an example, assume that the working stages of the hydraulic support include the stage of raising the support, the stage of lowering the support, the supporting stage, and the stage of moving the support. The number of hydraulic supports is n. For the i-th hydraulic support, when the target moment is t0, the target working stage where the i-th hydraulic support is located at t0 is the supporting stage, and the first start time of this stage is t1. Then the time difference between t0 and the first start time t1 of the target working stage where the i-th hydraulic support is located at t0 is (t0 - t1), and this time difference is determined as the first duration of the target working stage where the i-th hydraulic support is located at t0; taking this first duration as the value of the element of the dimension corresponding to the working stage in the working cycle time vector, and setting the values of the elements of the dimensions of other working stages as set values (such as 0), thereby generating the working cycle time vector of the i-th hydraulic support at t0. For example, the working cycle time vector of the i-th hydraulic support at t0 is: (T 支撑 ,T 升柱 ,T 降柱 ,T 移架 )=(t0 - t1,0,0,0);(6) Wherein, T 支撑 represents the dimension of the supporting stage, T 升柱 represents the dimension of the stage of raising the support, T 降柱 represents the dimension of the stage of lowering the support, T 移架 represents the dimension of the stage of moving the support.

[0080] Optionally, in some embodiments, for any hydraulic support, the determination process of the target telescopic amount of the moving support at any target moment may be as follows: for any target moment, determine the minimum value and the maximum value from the moving support height data when the safety valve is in the open state during the most recent safety valve opening cycle in the historical record corresponding to the target moment; determine the difference between the maximum value and the minimum value as the target telescopic amount of the moving support at the target moment.

[0081] Step S202, according to at least one statistical feature, use the target prediction model to obtain the opening probability of the safety valve of each hydraulic support within the future target time period.

[0082] It should be noted that the explanations of the target prediction model, the future target time period, and the opening probability in step S101 also apply to this embodiment and will not be elaborated here.

[0083] As an example, at least one statistical feature can be input into the target prediction model, and in response to the output of the target prediction model, obtain the opening probability of the safety valve of each hydraulic support within the future target time period.

[0084] To effectively obtain the target prediction model, as a possible implementation, the working data of multiple hydraulic supports within a set time period (such as half a year, 30 days, etc.) before the current time period can be obtained. Then, the working data of multiple hydraulic supports within the set time period before the current time period can be divided into a training set and a test set, and the initial prediction model can be trained using the training set and tested using the test set to obtain the target prediction model.

[0085] In one example, when the target prediction model includes a first bidirectional LSTM (Long Short-Term Memory) layer, a Dropout layer, a second bidirectional LSTM layer, and a Sigmoid layer, the forward and backward dependencies in the time series data can be extracted through the first bidirectional LSTM layer to capture the dynamic characteristics of the hydraulic system pressure change; then, the risk of overfitting can be reduced through the Dropout layer to improve the generalization ability of the model; further, deep time features can be mined through the second bidirectional LSTM layer, and finally, a probability prediction result can be generated through the Sigmoid output layer.

[0086] Step S203, determine the first risk sub-index value according to the opening probability of the safety valve of each hydraulic support within the future target time period.

[0087] Step S204, perform a first analysis on the mining data of the coal mining work in the current time period to obtain the second risk sub-index value.

[0088] Step S205: Perform a second analysis on the target working resistance nephogram of multiple hydraulic supports at the current moment to obtain the third risk sub-index value.

[0089] Step S206: Based on the first risk sub-index value, the second risk sub-index value, and the third risk sub-index value, identify the target abnormal types of multiple hydraulic supports.

[0090] It should be noted that the execution processes of steps S203 to S206 can refer to the execution processes of any embodiment of this application and will not be elaborated here.

[0091] In the method for identifying abnormal working resistance of hydraulic supports according to the embodiments of this application, by statistically analyzing the working data of multiple hydraulic supports in the current time period, at least one statistical feature is obtained; according to at least one statistical feature, using the target prediction model, the opening probability of the safety valve of each hydraulic support within the future target time period is obtained. Thus, by quantifying the statistical features of the hydraulic supports and combining the target prediction model, the accurate capture of the future opening probability of the safety valve is realized.

[0092] To clearly illustrate how to obtain the target working resistance nephogram at the current moment in the above embodiments of this application, this application also proposes a method for identifying abnormal working resistance of hydraulic supports.

[0093] Figure 3 It is a schematic flowchart of the method for identifying abnormal working resistance of hydraulic supports provided by another embodiment of this application.

[0094] As Figure 3 shown, based on any of the above embodiments of this application, the method may further include the following steps: Step S301: Based on the working data of multiple hydraulic supports in the current time period during the coal mining operation, use the target prediction model to predict the opening probability of the safety valve of each hydraulic support within the future target time period.

[0095] Step S302: Determine the first risk sub-index value according to each opening probability.

[0096] Step S303: Perform a first analysis on the mining data of the coal mining operation in the current time period to obtain the second risk sub-index value.

[0097] It should be noted that the execution processes of steps S301 to S303 can refer to the execution processes of any embodiment of this application and will not be elaborated here.

[0098] Step S304: Based on the first resistance values of multiple hydraulic supports within a preset historical duration before the current time period and the second resistance values in the current time period, predict the first predicted resistance values of each hydraulic support during the process of the coal face advancing forward to a position at a first preset length in front of the current coal face.

[0099] Among them, the preset historical duration can be preset, for example, it can be 90 days, 120 days, etc., and the present application does not limit its value.

[0100] Optionally, when the current time period includes multiple target moments, the first resistance value can be the average of the left-column resistance value and the right-column resistance value of the corresponding hydraulic support at any acquisition moment within the preset historical duration before the current time period; the second resistance value can be the average of the left-column resistance value and the right-column resistance value of the corresponding hydraulic support at any target moment. It should be noted that the time granularity of the acquisition moment can be coarser (or larger, lower precision) than that of the target moment. For example, the time granularity of the acquisition moment is in hours, and the granularity of the target moment is in minutes. It should also be noted that similar to the first resistance value and the second resistance value, the first predicted resistance value can be used to indicate the average of the left-column resistance value and the right-column resistance value of the corresponding hydraulic support, and the time granularity of the first predicted resistance value can be the same as that of the acquisition moment.

[0101] Among them, the first preset length can be preset, for example, it can be 100 meters, 120 meters, etc., and the present application does not limit this.

[0102] As an example, assume that the number of hydraulic supports is 150 and the current time period is 1 hour. The first resistance values of 150 hydraulic supports within 90 days before the current time period can be obtained. Among them, each hydraulic support has a corresponding first resistance value per hour, with a total of 32,400 data; the second resistance values corresponding to each hydraulic support per minute within the current time period can also be obtained, with a total of 9,000 data.

[0103] It can be understood that the coal face will advance forward as coal mining work progresses. Therefore, in the embodiments of the present application, based on the first resistance values of multiple hydraulic supports within a preset historical duration before the current time period and the second resistance values in the current time period, the IDW (Inverse Distance Weighting) algorithm can be used to obtain the first predicted resistance values of each hydraulic support at different positions or different times during the process of the coal face advancing forward to a position at a first preset length in front of the current coal face.

[0104] Step S305: Determine the target distance according to the periodic weighting step distance in the most recent set number of cycles.

[0105] Among them, the set number of times can be preset, for example, it can be 3 times, etc., and the present application does not limit its value.

[0106] As an example, assuming the set number of times is n, the step distance can be pressed according to the recent n cycles, and the target distance can be determined according to the following formula: ; (7) where d is the target distance, and d i is the step distance pressing in the i-th cycle among the step distance pressings in the recent n cycles.

[0107] Step S306: Update the first predicted resistance value of each hydraulic support at different positions in the target mining area to the set value.

[0108] Among them, the target mining area is the area within the second set length range in front (in the same direction as the advancing direction of the mining face, i.e., the mining direction) when the mining face is at a target distance from the current mining face. It should be noted that the size of the target mining area can be determined by the second set length, the number of hydraulic supports, and the support width of the hydraulic supports.

[0109] Among them, the second set length can be preset, for example, it can be 3 meters, 4 meters, etc., and the present application does not limit its value. Optionally, the second set length can be determined based on the average daily mining speed.

[0110] Such as Figure 4 shown, the current mining face is at position A, the advancing direction of the mining face (i.e., the mining direction) is as Figure 4 shown by the arrow direction in the figure. The distance between position B and position A is the target distance, and area C is the area within the second set length d in front of position B. Among them, the size of area C is d×(n*L), where n is the number of hydraulic supports and L is the support width.

[0111] Among them, the set value can be preset, for example, it can be 0, and the present application does not limit its value.

[0112] That is to say, the first predicted resistance values of each hydraulic support at different positions in the target mining area obtained by prediction are adjusted and updated to the set value.

[0113] Step S307: Generate a first working resistance cloud map according to the updated first predicted resistance value.

[0114] In one example, according to the updated first predicted resistance values of each hydraulic support at different positions in the target mining area and the first predicted resistance values in the unupdated area during the process of each hydraulic support advancing forward to the position at the first set length in front of the current mining face as the mining face advances forward, a first working resistance cloud map is generated.

[0115] As an example, assume that the number of hydraulic supports is 150 and the current time period is 1 hour. The first resistance values of 150 hydraulic supports within 90 days before the current time period can be obtained. Among them, each hydraulic support has a corresponding first resistance value per hour, with a total of 32,400 data; the second resistance values corresponding to each hydraulic support per minute within the current time period can also be obtained, with a total of 9,000 data; the position of the current working face is as Figure 5 shown. At position a, according to the updated first predicted resistance values corresponding to each hydraulic support within 100 meters in front of the current mining face, the generated first working resistance cloud map is as Figure 5 shown in the area C corresponding to the red frame in Figure 5 shown. Among them, as Figure 5 shown, 150 hydraulic supports are arranged in the arrangement direction in

[0116] Step S308, according to the change amount of the first resistance values of multiple hydraulic supports within the set historical duration and the change amount of the second resistance values within the current time period, predict the change amount of the predicted resistance values of each hydraulic support during the process of advancing forward to the position at the first set length in front of the current mining face as the mining face advances forward.

[0117] Among them, when the current time period includes multiple target moments, the change amount of the first resistance values can be the change amount of the first resistance values at any two adjacent acquisition moments within the set historical duration before the current time period for the corresponding hydraulic support, and the change amount of the second resistance values can be the change amount of the second resistance values at any two adjacent target moments for the corresponding hydraulic support.

[0118] In the embodiments of the present application, according to the change amount of the first resistance values of multiple hydraulic supports within the set historical duration and the change amount of the second resistance values within the current time period, the IDW algorithm can be used to obtain the change amount of the predicted resistance values of each hydraulic support during the process of advancing forward to the position at the first set length in front of the current mining face as the mining face advances forward.

[0119] Step S309, generate a first time growth rate cloud map according to the change amount of the predicted resistance values; among them, the size of the first time growth rate cloud map is the same as that of the first working resistance cloud map.

[0120] Step S310: Superimpose the first working resistance cloud map and the first time growth rate cloud map to obtain the first superimposed working resistance cloud map.

[0121] As an example, when both the first working resistance cloud map and the first time growth rate cloud map are RGB (Red, Green, Blue) images, for any pixel point in the first working resistance cloud map, there is a pixel point in the first time growth rate cloud map that matches the position of this pixel point. Denote the pixel points that match in position in the first working resistance cloud map and the first time growth rate cloud map as a pair of matching pixel points. For any pair of matching pixel points, obtain the minimum value of this pair of matching pixel points in any color channel. For example, there is a pair of matching pixel points of pixel point 1 and pixel point 2, where pixel point 1 belongs to the first working resistance cloud map and pixel point 2 belongs to the first time growth rate cloud map. In the R channel, the value of pixel point 1 in the R channel is 156, and the value of pixel point 2 in the R channel is 99, then take the minimum value 99. Generate the color value of the pixel point in the first superimposed working resistance cloud map that matches the position of this pair of matching pixel points with the minimum values of this pair of matching pixel points in each color channel. Thus, the first superimposed working resistance cloud map can be obtained.

[0122] Step S311: Determine the first superimposed working resistance cloud map as the target working resistance cloud map at the current moment.

[0123] Optionally, in some embodiments, a second working resistance cloud map can also be generated according to the second resistance value; a second time growth rate cloud map can be generated according to the change amount of the second resistance value; wherein, the second time growth rate cloud map has the same size as the second working resistance cloud map; superimpose the second working resistance cloud map and the second time growth rate cloud map to obtain the second superimposed working resistance cloud map; determine the second superimposed working resistance cloud map as the target working resistance cloud map at the current moment. Among them, the second working resistance cloud map is as Figure 5 shown in the area B corresponding to the yellow box in the figure.

[0124] Optionally, in some embodiments, the first superimposed working resistance cloud map and the second superimposed working resistance cloud map can also be combined to obtain a combined working resistance cloud map; determine the combined working resistance cloud map as the target working resistance cloud map at the current moment.

[0125] Step S312: Perform a second analysis on the target working resistance cloud map of multiple hydraulic supports at the current moment to obtain the third risk sub-index value.

[0126] It should be noted that the execution process of step S312 can refer to the execution process of any embodiment of this application, and will not be elaborated here.

[0127] As a possible implementation, the target working resistance cloud map can be converted to the HSV (Hue, Saturation, Value) color space to obtain a target picture; analyze the hue of the pixel points in the target picture to determine the target proportion of the pixel points with the target color in the target picture; determine the value of the third risk sub-index according to the target proportion and the working stages of multiple hydraulic supports at the current moment.

[0128] Among them, the colors of the pixel points in the target picture can include four colors: red (hue 0°), yellow (hue 60°), green (hue 120°), and blue (hue 240°).

[0129] Among them, in the target picture, the resistance value can have a positive correlation with the hue, that is, the higher the hue value, the greater the resistance value of the hydraulic support indicated by the corresponding area.

[0130] Among them, the target color can be at least one of red, yellow, green, and blue. For example, it can be red and yellow, and this application does not limit this.

[0131] As an example, for any hydraulic support, when the column pressure of the hydraulic support at the current moment > 25 MPa, the pressure fluctuation rate < ±2 MPa / min, the horizontal error of the roof beam < 1.5°, the pressure difference between adjacent supports < 10 MPa, and the expansion angle of the rib protection plate > 75°, it indicates that the hydraulic support is in the support stage at the current moment. When the speed of the push cylinder of the hydraulic support at the current moment is in the range of 0.1 - 0.3 m / s, the column pressure relief time is 3 - 5 s, the sudden increase in the front tilt angle of the roof beam > 8°, and the infrared positioning deviation < 50 mm, it indicates that the hydraulic support is in the stage of moving the support at the current moment.

[0132] As an example, assuming the target colors are red and yellow, when the working stages of more than 80% of the multiple hydraulic supports at the current moment are the support stage, the relationship between the target proportion and the value of the third risk sub-index R3 is shown in Table 3: Table 3 Relationship between the target proportion and the value of the third risk sub-index R3

[0133] When the working stages of more than 80% of the multiple hydraulic supports at the current moment are the stage of moving the support, the relationship between the target proportion and the value of the third risk sub-index R3 is shown in Table 2: Table 4 Relationship between the target proportion and the value of the third risk sub-index R3

[0134] In other cases, the value of the third risk sub-index R3 can be set to 0.5.

[0135] Step S313: Based on the first risk sub - index value, the second risk sub - index value, and the third risk sub - index value, identify the target abnormal types of multiple hydraulic supports.

[0136] It should be noted that the execution process of step S313 can refer to the execution process of any embodiment of this application and will not be elaborated here.

[0137] In the method for identifying abnormal working resistance of hydraulic supports according to the embodiments of this application, by predicting the first predicted resistance value of each hydraulic support during the process of the coal winning face advancing forward to the position at the first set length in front of the current coal winning face based on the first resistance value of multiple hydraulic supports within the most recent first set time period and the second resistance value within the most recent second set time period; determining the target distance according to the periodic weighting step distance of the most recent set number of times; updating the first predicted resistance value of each hydraulic support at different positions within the target mining area to the set value; where the target mining area is the area within the second set length in front when the coal winning face is at the target distance from the current coal winning face; generating the first working resistance cloud map according to the updated first predicted resistance value; predicting the change amount of the predicted resistance value of each hydraulic support during the process of the coal winning face advancing forward to the position at the first set length in front of the current coal winning face based on the change amount of the first resistance value of multiple hydraulic supports within the most recent first set time period and the change amount of the second resistance value within the most recent second set time period; generating the first time - speed - increase cloud map according to the change amount of the predicted resistance value; where the first time - speed - increase cloud map has the same size as the first working resistance cloud map; superimposing the first working resistance cloud map and the first time - speed - increase cloud map to obtain the first superimposed working resistance cloud map; and determining the first superimposed working resistance cloud map as the target working resistance cloud map at the current moment. Thus, through the fusion of the resistance value and the change amount of the resistance value, an effective and accurate acquisition of the target working resistance cloud map is achieved, making the constructed target working resistance cloud map more capable of truly reflecting the resistance values of each hydraulic support at different positions during the advancement of the coal winning work.

[0138] To clearly illustrate the method for identifying abnormal working resistance of hydraulic supports in this application, the above process will be described in detail below with examples. As an example, the method for identifying abnormal working resistance of hydraulic supports may include the following steps: Step 1: Obtain sensor data such as support resistance pressure parameters, support column displacement data, and shearer mining parameters. Real-time collect the support resistance pressure parameters, shearer mining parameters, and support column displacement data in the support electro-hydraulic control system through the OPC (Object Linking and Embedding (OLE) for Process Control, a key standard for data exchange and device communication in the industrial automation field) protocol; the support resistance pressure parameters include support number, time, left column resistance value, right column resistance value, support stage time (which can include start time and / or end time), start time of the lowering column stage (which can include start time and / or end time), start time of the support moving stage (which can include start time and / or end time), lifting column stage time (which can include start time and / or end time), support attitude, working cycle time, safety valve opening pressure, safety valve opening duration, live column shrinkage amount during safety valve opening, safety valve closing pressure, time interval between two safety valve openings, and support stiffness, etc. The shearer mining parameters include shearer number, mining progress, cutting height, shearer traction direction, timestamp, etc. The support column displacement data includes support number, timestamp, and live column height.

[0139] Optionally, in some embodiments, after obtaining the above data, according to the requirements of the specification, construct the required data format in accordance with the data access content, message queue name, message content, and data item description, and upload it to the corresponding Kafka message queue.

[0140] Step 2: Integrate multi-source data through Logstash technology; By calling the Logstash component, configure the Pipelines file according to the Kafka topic to obtain the uploaded message information from Kafka, parse the string-type message into JSON format according to the rules, and add fields such as unique identifier, processing time, Kafka topic name, Kafka offset, etc., and store it in the corresponding table of Clickhouse as the original data backup. At the same time, send it to the unified warn_json topic of Kafka. For the JSON format, only need to supplement the unique identifier, processing time, Kafka topic name, and Kafka offset fields and send them to the warn_json topic. Through the above data processing, the multi-source data is unified and summarized into the warn_json topic of Kafka, and subsequent data is obtained from the warn_json in real time (i.e., the current time period) data.

[0141] Step 3: Construct a support resistance safety valve opening prediction model (denoted as the target prediction model in this application); Step 4: First, clean the real-time data using a Bloom filter, and then construct a feature vector for the cleaned real-time data, and input it into the S support resistance safety valve opening prediction model to predict the opening probability of the safety valve; Step 5: Determine the warning risk coefficient R1 of the support resistance safety valve (denoted as the first risk sub-index value in this application) according to the opening probability of the safety valve; Step 6: Use the finite element method to determine the geological risk coefficient R2 (denoted as the second risk sub-index value in this application) for the coal and rock stratum structure model in the stope (i.e., the MiningFEM model); Step 7: Based on the resistance cloud map formed by multi-index dynamic fusion (denoted as the target working resistance cloud map in this application), determine the support area risk coefficient R3 (denoted as the third risk sub-index value in this application); Step 8: Adopt the support resistance adaptive dynamic weight evaluation model to obtain the target abnormal types of multiple hydraulic supports.

[0142] Among them, the support resistance adaptive dynamic weight evaluation model dynamically adjusts the weights of each risk factor by comprehensively considering the warning risk coefficient R1 of the support resistance safety valve, the geological risk coefficient R2, and the support area risk coefficient R3, so as to determine the abnormal types of hydraulic supports.

[0143] It should be noted that when it is determined that the support resistance stress is abnormal, real-time alarm can be triggered, and a warning processing mechanism can be triggered.

[0144] In summary, the method for identifying abnormal working resistance of hydraulic supports in this application can combine the warning risks of support resistance safety valves, geological risks, and support area risks to automatically and quickly identify the abnormal types of hydraulic support working resistance, improving the timeliness and effectiveness of identifying abnormal working resistance of hydraulic supports.

[0145] As above Figures 1 to 3 Corresponding to the method for identifying abnormal working resistance of hydraulic supports provided in the above Figures 1 to 3 embodiment, this application also provides a device for identifying abnormal working resistance of hydraulic supports. Since the device for identifying abnormal working resistance of hydraulic supports provided in the embodiment of this application corresponds to the

[0146] Figure 6 method for identifying abnormal working resistance of hydraulic supports provided in the above

[0147] embodiment, the implementation manner of the method for identifying abnormal working resistance of hydraulic supports is also applicable to the device for identifying abnormal working resistance of hydraulic supports provided in the embodiment of this application, and will not be described in detail in the embodiment of this application. Figure 6 As shown, the device 600 for identifying abnormal working resistance of hydraulic supports may include: a prediction module 601, a first determination module 602, a first analysis module 603, a second analysis module 604, and an identification module 605.

[0148] Among them, the prediction module 601 is used to predict the opening probability of the safety valve of each hydraulic support within the future target time period based on the working data of multiple hydraulic supports in the current time period during mining work, using a target prediction model; wherein the current time period includes the current moment.

[0149] The first determination module 602 is used to determine a first risk sub-index value according to each opening probability; wherein the first risk sub-index value is determined based on the number of target hydraulic supports whose opening probabilities meet set conditions and whose layout positions are continuously adjacent to each other among multiple hydraulic supports.

[0150] The first analysis module 603 is used to perform a first analysis on the mining data of the mining work in the current time period to obtain a second risk sub-indicator value.

[0151] The second analysis module 604 is used to perform a second analysis on the target working resistance cloud diagrams of the multiple hydraulic supports at the current moment to obtain a third risk sub-indicator value.

[0152] The identification module 605 is used to identify target abnormality types of multiple hydraulic supports based on the first risk sub-indicator value, the second risk sub-indicator value and the third risk sub-indicator value.

[0153] In a possible implementation of an embodiment of the present application, the prediction module 601 is used to: perform statistical analysis on the working data of multiple hydraulic supports in the current time period to obtain at least one statistical feature; and based on at least one statistical feature, use a target prediction model to obtain the probability of opening the safety valve of each hydraulic support within a future target duration.

[0154] In a possible implementation of the embodiment of the present application, the current time period includes multiple target moments, and the work data includes at least one of the following: The left column resistance value and the right column resistance value at any target moment; The left initial support force and the right initial support force at any target moment; The target working stage at any target moment and the first starting time of the target working stage; The second start time and end time when the safety valve is in the open state in the most recent safety valve opening cycle in the historical records corresponding to any target time; The plunger height data when the safety valve is in the open state during the most recent safety valve opening cycle in the historical records corresponding to any target time.

[0155] In a possible implementation of the embodiment of the present application, the statistical feature includes at least one of the following: The target resistance value of each hydraulic support at any target time; wherein the target resistance value is determined based on the left column resistance value and the right column resistance value of the corresponding hydraulic support; The initial support force qualification rate of multiple hydraulic supports at any target moment; wherein, the initial support force qualification rate is determined based on the left initial support force and the right initial support force of multiple hydraulic supports; The working cycle time vector of each hydraulic support at any target moment; wherein, the working cycle time vector is generated based on the target working stage where the corresponding hydraulic support is located at the corresponding target moment and the first start time of the target working stage; The target duration of each hydraulic support at any target moment; wherein, the target duration is based on the second start time and the end time when the safety valve is in the open state during the most recent safety valve opening cycle in the corresponding historical record of the corresponding hydraulic support; The target telescopic amount of the moving column of each hydraulic support at any target moment; wherein, the target telescopic amount of the moving column is determined based on the moving column height data when the safety valve is in the open state during the most recent safety valve opening cycle in the corresponding historical record of the corresponding hydraulic support.

[0156] In a possible implementation manner of the embodiment of the present application, the hydraulic support working resistance abnormality recognition device 600 may further include: A second determination module, configured to: for any target moment, determine whether both the left initial support force and the right initial support force of any hydraulic support at the target moment are qualified; in the case where both the left initial support force and the right initial support force of the hydraulic support at the target moment are qualified, determine the hydraulic support as the first hydraulic support with qualified initial support force; count the first hydraulic supports among the multiple hydraulic supports to obtain a first quantity; and determine the initial support force qualification rate of the multiple hydraulic supports at the target moment according to the first quantity and the quantity of the multiple hydraulic supports.

[0157] In a possible implementation manner of the embodiment of the present application, the hydraulic support working resistance abnormality recognition device 600 may further include: a generation module, configured to: for any target moment, determine the first duration of the target working stage where the hydraulic support is located at the target moment based on the time difference between the target moment and the first start time of the target working stage where the hydraulic support is located at the target moment; and generate the working cycle time vector of the hydraulic support at the target moment according to the first duration of the target working stage where the hydraulic support is located at the target moment.

[0158] In a possible implementation manner of the embodiment of the present application, the abnormal working resistance recognition device 600 of the hydraulic support may further include an acquisition module, configured to: predict a first predicted resistance value of each hydraulic support during the process of advancing the fully mechanized caving face forward to a position at a first set length in front of the current fully mechanized caving face according to the first resistance values of multiple hydraulic supports within a set historical duration before the current time period and the second resistance values in the current time period; determine a target distance according to the periodic weighting step distance in the most recent set number of times; update the first predicted resistance values of each hydraulic support at different positions within the target mining area to set values; where the target mining area is an area within a second set length in front when the fully mechanized caving face is at a target distance from the current fully mechanized caving face; generate a first working resistance cloud map according to the updated first predicted resistance values; predict a change in the predicted resistance value of each hydraulic support during the process of advancing the fully mechanized caving face forward to a position at a first set length in front of the current fully mechanized caving face according to the change in the first resistance value of multiple hydraulic supports within the set historical duration and the change in the second resistance value in the current time period; generate a first time growth rate cloud map according to the change in the predicted resistance value; where the first time growth rate cloud map has the same size as the first working resistance cloud map; superimpose the first working resistance cloud map and the first time growth rate cloud map to obtain a first superimposed working resistance cloud map; and determine the first superimposed working resistance cloud map as the target working resistance cloud map at the current moment.

[0159] In a possible implementation manner of the embodiment of the present application, the acquisition module is further configured to: generate a second working resistance cloud map according to the second resistance value; generate a second time growth rate cloud map according to the change in the second resistance value; where the second time growth rate cloud map has the same size as the second working resistance cloud map; superimpose the second working resistance cloud map and the second time growth rate cloud map to obtain a second superimposed working resistance cloud map; and determine the second superimposed working resistance cloud map as the target working resistance cloud map at the current moment.

[0160] In a possible implementation manner of the embodiment of the present application, the acquisition module is further configured to: merge the first superimposed working resistance cloud map and the second superimposed working resistance cloud map to obtain a merged working resistance cloud map; and determine the merged working resistance cloud map as the target working resistance cloud map at the current moment.

[0161] In a possible implementation manner of the embodiment of the present application, the second analysis module 604 is configured to: convert the target working resistance cloud map to the HSV color space to obtain a target picture; where the target picture includes four colors: red, yellow, green, and blue; analyze the hue of the pixel points in the target picture to determine the target proportion of the pixel points with the target color in the target picture; and determine a third risk sub - index value according to the target proportion and the working stage of multiple hydraulic supports at the current moment.

[0162] The device for identifying abnormal working resistance of hydraulic supports in the embodiment of the present application predicts the opening probability of the safety valve of each hydraulic support within the future target time length by using the target prediction model based on the working data of multiple hydraulic supports in the current time period during the mining work; wherein the current time period includes the current moment; according to each opening probability, the first risk sub-index value is determined; wherein the first risk sub-index value is determined based on the number of target hydraulic supports whose opening probability meets the set conditions and whose layout positions are continuously adjacent among the multiple hydraulic supports; a first analysis is performed on the mining data of the mining work in the current time period to obtain a second risk sub-index value; a second analysis is performed on the target working resistance cloud map of multiple hydraulic supports at the current moment to obtain a third risk sub-index value; based on the first risk sub-index value, the second risk sub-index value and the third risk sub-index value, the target abnormal type of multiple hydraulic supports is identified. Thus, the working data of the hydraulic support, the mining data of the mining work and the working resistance cloud map of the hydraulic support can be combined to automatically and quickly identify the abnormal working resistance stress results of the hydraulic support, thereby improving the timeliness and effectiveness of the recognition of abnormal working resistance of the hydraulic support.

[0163] In order to implement the above-mentioned embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method for identifying abnormal working resistance of a hydraulic support provided in the above-mentioned embodiments.

[0164] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method for identifying abnormal working resistance of a hydraulic support provided in the above embodiments.

[0165] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which, when executed by a processor, implements the method for identifying abnormal working resistance of a hydraulic support provided in the above embodiments.

[0166] The collection, storage, use, processing, transmission, provision and application of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0167] It should be noted that personal information from users should be collected for legal and reasonable purposes and should not be shared or sold outside of such legal uses. In addition, such collection / sharing should be carried out after obtaining the informed consent of the users, including but not limited to notifying the users to read the user agreement / user notice before using the function and signing an agreement / authorization including authorizing the relevant user information. In addition, any necessary steps should be taken to defend and safeguard access to such personal information data and to ensure that others with access to the personal information data comply with their privacy policies and procedures.

[0168] This application is expected to provide an implementation for users to selectively block the use or access to personal information data. That is, this application is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by restricting data collection and deleting the data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of the users.

[0169] In the descriptions of the foregoing embodiments, the descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples.

[0170] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as controlling or implying relative importance or implicitly indicating the quantity of the technical features controlled. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0171] Any process or method description shown in the flowchart or described in other ways herein may be understood to represent a module, segment, or part of code including one or more executable instructions for implementing a customized logical function or process, and the scope of the preferred implementation of the present application includes additional implementations, where the functions may be executed not in the order shown or discussed, including in a substantially simultaneous manner according to the functions involved or in a reverse order, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0172] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0173] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or combinations thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well-known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGA), field-programmable gate arrays (FPGA), etc.

[0174] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0175] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0176] The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for identifying abnormal working resistance of a hydraulic support, characterized in that: The method comprises: Based on the working data of multiple hydraulic supports in the current time period during the mining work, a target prediction model is used to predict the opening probability of the safety valve of each hydraulic support within the future target time period; wherein the current time period includes the current moment; Determine a first risk sub-index value according to each of the opening probabilities; wherein the first risk sub-index value is determined based on the number of target hydraulic supports whose opening probabilities meet set conditions and whose layout positions are continuously adjacent to each other among the multiple hydraulic supports; Performing a first analysis on the mining data of the mining work in the current time period to obtain a second risk sub-indicator value; Performing a second analysis on the target working resistance cloud diagrams of the plurality of hydraulic supports at the current moment to obtain a third risk sub-index value; Based on the first risk sub-indicator value, the second risk sub-indicator value and the third risk sub-indicator value, target abnormality types of the plurality of hydraulic supports are identified.

2. The method according to claim 1, characterized in that Based on the working data of multiple hydraulic supports in the current time period during the mining operation, the target prediction model is used to predict the opening probability of the safety valve of each hydraulic support within the future target time period, including: Performing statistical analysis on the working data of the plurality of hydraulic supports in the current time period to obtain at least one statistical feature; According to the at least one statistical feature, the target prediction model is used to obtain the opening probability of the safety valve of each hydraulic support within a future target duration.

3. The method according to claim 2, characterized in that The current time period includes a plurality of target moments, and the work data includes at least one of the following: The left column resistance value and the right column resistance value at any said target time; The left initial support force and the right initial support force at any target moment; The target working stage at any target moment and the first starting time of the target working stage; The second start time and end time when the safety valve is in the open state in the most recent safety valve opening cycle in the historical records corresponding to any of the target times; The plunger height data when the safety valve is in the open state in the most recent safety valve opening cycle in the historical record corresponding to any of the target moments.

4. The method according to claim 3, characterized in that The statistical features include at least one of the following: a target resistance value of each of the hydraulic supports at any target time; wherein the target resistance value is determined based on the left column resistance value and the right column resistance value of the corresponding hydraulic support; The qualified rate of the initial support force of the plurality of hydraulic supports at any of the target moments; wherein the qualified rate of the initial support force is determined based on the left initial support force and the right initial support force of the plurality of hydraulic supports; A working cycle time vector of each of the hydraulic supports at any of the target moments; wherein the working cycle time vector is generated based on the target working stage of the corresponding hydraulic support at the corresponding target moment and the first starting time of the target working stage; The target duration of each hydraulic support at any target moment; wherein the target duration is based on the second start time and end time when the safety valve of the corresponding hydraulic support is in the open state in the most recent safety valve opening cycle in the corresponding historical records; The target piston downward retraction amount of each hydraulic support at any target moment; wherein, the target piston downward retraction amount is determined based on the piston height data of the corresponding hydraulic support when the safety valve is in the open state in the most recent safety valve opening cycle in the corresponding historical records.

5. The method according to claim 4, characterized in that The process of determining the qualified rate of the initial support force of the plurality of hydraulic supports at any target time includes: For any of the target moments, determining whether the left initial support force and the right initial support force of any of the hydraulic supports at the target moment are both qualified; In the case where the left initial supporting force and the right initial supporting force of the hydraulic support at the target time are both qualified, determining the hydraulic support as the first hydraulic support with qualified initial supporting force; Counting the first hydraulic supports among the plurality of hydraulic supports to obtain a first quantity; According to the first number and the number of the plurality of hydraulic supports, an initial support force qualification rate of the plurality of hydraulic supports at the target time is determined.

6. The method according to claim 4, characterized in that For any of the hydraulic supports, the process of generating the working cycle time vector of the hydraulic support at any of the target moments includes: For any of the target moments, based on the time difference between the target moment and the first start time of the target working stage of the hydraulic support at the target moment, determine the first duration of the target working stage of the hydraulic support at the target moment; A working cycle time vector of the hydraulic support at the target moment is generated according to a first duration of the target working phase of the hydraulic support at the target moment.

7. The method according to claim 1, characterized in that The process of obtaining the target work resistance cloud map at the current moment includes: According to the first resistance values ​​of the plurality of hydraulic supports within the set historical time period before the current time period and the second resistance values ​​in the current time period, a first predicted resistance value of each hydraulic support in the process of advancing forward with the mining working face to a first set length position in front of the current mining working face is predicted; Determine the target distance by pressing the step distance according to the cycle of the most recent set number of times; The first predicted resistance value of each hydraulic support at different positions in the target mining area is updated to a set value; wherein the target mining area is the area within a second set length range in front of the mining working face when the mining working face is located at the target distance from the current mining working face; Generate a first working resistance cloud diagram according to the updated first predicted resistance value; According to the first resistance value changes of the plurality of hydraulic supports within the set historical time period and the second resistance value changes in the current time period, the predicted resistance value changes of each hydraulic support in the process of advancing forward along the mining working face to a first set length position in front of the current mining working face are predicted; Generate a first time speed-up cloud diagram according to the predicted resistance value change; wherein the first time speed-up cloud diagram has the same size as the first working resistance cloud diagram; Superimposing the first working resistance cloud map and the first time speed increase cloud map to obtain a first superimposed working resistance cloud map; The first superimposed working resistance cloud map is determined as the target working resistance cloud map at the current moment.

8. The method according to claim 7, characterized in that The method further comprises: generating a second working resistance cloud diagram according to the second resistance value; Generate a second time speed-up cloud graph according to the second resistance value change; wherein the second time speed-up cloud graph has the same size as the second working resistance cloud graph; Superimposing the second working resistance cloud map and the second time speed increase cloud map to obtain a second superimposed working resistance cloud map; The second superimposed working resistance cloud map is determined as the target working resistance cloud map at the current moment.

9. The method according to claim 8, characterized in that The method further comprises: Merging the first superimposed working resistance cloud map and the second superimposed working resistance cloud map to obtain a combined working resistance cloud map; The combined work resistance cloud map is determined as the target work resistance cloud map at the current moment.

10. The method according to any one of claims 1 to 9, characterized in that: The second analysis of the target working resistance cloud diagrams of the plurality of hydraulic supports at the current moment to obtain a third risk sub-index value includes: Convert the target working resistance cloud map into the HSV color space to obtain a target image; wherein the target image includes four colors: red, yellow, green and blue; Analyze the hue of the pixels in the target image to determine the target proportion of the pixels in the target image whose color is the target color; The third risk sub-indicator value is determined according to the target proportion and the working stage of the multiple hydraulic supports at the current moment.

Images